TY - JOUR AU - Makarious, Mary B. AU - Leonard, Hampton L. AU - Vitale, Dan AU - Iwaki, Hirotaka AU - Sargent, Lana AU - Dadu, Anant AU - Violich, Ivo AU - Hutchins, Elizabeth AU - Saffo, David AU - Bandres-Ciga, Sara AU - Kim, Jonggeol Jeff AU - Song, Yeajin AU - Maleknia, Melina AU - Bookman, Matt AU - Nojopranoto, Willy AU - Campbell, Roy H. AU - Hashemi, Sayed Hadi AU - Botia, Juan A. AU - Carter, John F. AU - Craig, David W. AU - Van Keuren-Jensen, Kendall AU - Morris, Huw R. AU - Hardy, John A. AU - Blauwendraat, Cornelis AU - Singleton, Andrew B. AU - Faghri, Faraz AU - Nalls, Mike A. TI - Multi-modality machine learning predicting Parkinson’s disease JO - npj Parkinson's Disease VL - 8 IS - 1 SN - 2373-8057 CY - London [u.a.] PB - Nature Publ. Group M1 - DZNE-2022-00445 SP - 35 PY - 2022 AB - Personalized medicine promises individualized disease prediction and treatment. The convergence of machine learning (ML) and available multimodal data is key moving forward. We build upon previous work to deliver multimodal predictions of Parkinson’s disease (PD) risk and systematically develop a model using GenoML, an automated ML package, to make improved multi-omic predictions of PD, validated in an external cohort. We investigated top features, constructed hypothesis-free disease-relevant networks, and investigated drug–gene interactions. We performed automated ML on multimodal data from the Parkinson’s progression marker initiative (PPMI). After selecting the best performing algorithm, all PPMI data was used to tune the selected model. The model was validated in the Parkinson’s Disease Biomarker Program (PDBP) dataset. Our initial model showed an area under the curve (AUC) of 89.72 LB - PUB:(DE-HGF)16 C2 - pmc:PMC8975993 C6 - pmid:35365675 DO - DOI:10.1038/s41531-022-00288-w UR - https://pub.dzne.de/record/163706 ER -